Klasifikasi Intonasi Wicara Berbasis Sinyal EMG otot Leher

Fatchul, Arifin, M. T. (2013) Klasifikasi Intonasi Wicara Berbasis Sinyal EMG otot Leher. Artikel Disertasi Doktor.

[img]
Preview
Text
Artikel Jurnal International - Telah diterima.pdf

Download (454kB) | Preview

Abstract

Human voice intonation is affected by pitch and loudness. Pitch is related to the frequency of human voice, while Loudness is related to the magnitude of human voice. Someone who does not have vocal cords, He has no ability to produce voice and speech. This problem is suffered by laryngectomy patients. Over half of all laryngectomy patients worldwide are using electrolarynx for the rehabilitation of their speech ability. Unfortunately, the electrolarynx voice is monotonic and flatted intonation. Small changes in pitch and loudness of electrolarynx will give a better expression in laryngectomy patients. Previous researches have focused on utilization of Electromyography (EMG) signal of neck muscle for only pitch control. In this research, the relationship between human voice intonation (i.e., frequency and magnitude) and EMG signals of neck muscles was studied by looking for their correlation and their mutual information. Human voice signal and EMG signal of neck muscle were recorded simultaneuosly while subjects were saying “A” with varying intonation. The EMG signal of neck muscle was processed using amplifying, filtering, rectifying and “moving average” process. On the other hand, the human voice was processed by FFT Algorithm to obtain magnitude and fundamental frequency. The result shows that the correlation coefficient between human voice magnitudes and EMG signal of neck muscle is 0.93, while the correlation coefficient between human voice frequency and EMG signal of neck muscle is 0.88. Moreover, the mutual information between human voice magnitudes and EMG signal of neck muscle is 1.07, while the mutual information between human voice frequency and EMG signal of neck muscle is 0.65. These results show that the relationship between human voice magnitudes and EMG signal of neck muscle is stronger than the relationship between human voice frequencies and EMG signal of neck muscle. Therefore, it is more appropriate to use the EMG signal of neck muscle for controlling loudness of electrolarynx than that of the pitch of electrolarynx.

Item Type: Article
Additional Information: LAPORAN AKHIR PENELITIAN DISERTASI DOKTOR 2013
Uncontrolled Keywords: Neck muscle electromyography signal, Loudness of electrolarynx voice, Laryngectomies patients, Corerrelation, Mutual Information
Subjects: LPPM
Divisions: LPPM - Lembaga Penelitian dan Pengabdian kepada Masyarakat
Depositing User: LPPM UNY
Date Deposited: 07 Jul 2015 01:21
Last Modified: 07 Jul 2015 01:21
URI: http://eprints.uny.ac.id/id/eprint/22779

Actions (login required)

View Item View Item